transformer.yaml

name: Transform image data

on:
  schedule:
    - cron: "45 5 * * *"
  workflow_dispatch:

permissions:
  id-token: write
  contents: read

jobs:
  parser:
    name: "Transform image data"
    runs-on: ubuntu-latest
    steps:
      - uses: "actions/checkout@v3"

      - name: Configure AWS credentials
        uses: aws-actions/configure-aws-credentials@v1-node16
        with:
          role-to-assume: arn:aws:iam::426579533370:role/github_actions_image_transformer
          role-duration-seconds: 1800
          aws-region: us-east-2

      - name: Bootstrap poetry
        run: pipx install poetry

      - name: Update PATH
        if: ${{ matrix.os != 'Windows' }}
        run: echo "$HOME/.local/bin" >> $GITHUB_PATH

      - name: Configure poetry
        run: poetry config virtualenvs.in-project true

      - name: Set up cache
        uses: actions/cache@v3
        id: cache
        with:
          path: .venv
          key: venv-${{ runner.os }}-${{ steps.full-python-version.outputs.version }}-${{ hashFiles('**/poetry.lock') }}

      - name: Ensure cache is healthy
        if: steps.cache.outputs.cache-hit == 'true'
        run: |
          # Using `timeout` is a safeguard against the Poetry command hanging for some reason.
          timeout 10s poetry run pip --version || rm -rf .venv

      - name: Install dependencies
        run: |
          poetry install
          pipx install s3cmd

      - name: Download from S3
        run: |
          s3cmd sync --acl-public --delete-removed --guess-mime-type --no-mime-magic \
            s3://cloudx-json-bucket/raw/ $(pwd)/raw/

      - name: run transformer
        run: |
          poetry run cloudimagedirectory-transformer --origin.path=$(pwd)/raw --destination.path=$(pwd)/images --image.api.version v1 --input.files=none --filter.until=default

      - name: Upload to S3
        run: |
          s3cmd sync --acl-public --mime-type application/json \
            $(pwd)/images/ s3://cloudx-json-bucket/images/